© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 23738
    Prev
    Next
    INDEX
    Explanations

    comparisons or relationships expressed through the use of "wise."

    oai_token-act-pair · gpt-3.5-turbo

    references to various forms or aspects of wisdom

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¦ļéĨĴ
    -0.71
     Nou
    -0.68
     cellul
    -0.66
    gdala
    -0.63
    bern
    -0.60
     Klu
    -0.59
     Webster
    -0.59
     Explos
    -0.59
    enf
    -0.58
     Mé
    -0.57
    POSITIVE LOGITS
    wise
    1.18
    lihood
    1.16
    ly
    0.85
    liness
    0.81
    etheless
    0.80
    ellery
    0.77
    ably
    0.76
    eyed
    0.75
    terday
    0.73
    forward
    0.71
    Activations Density 0.005%

    No Known Activations